CN110532229A - Instrument of evidence search method, device, computer equipment and storage medium - Google Patents
Instrument of evidence search method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110532229A CN110532229A CN201910645277.2A CN201910645277A CN110532229A CN 110532229 A CN110532229 A CN 110532229A CN 201910645277 A CN201910645277 A CN 201910645277A CN 110532229 A CN110532229 A CN 110532229A
- Authority
- CN
- China
- Prior art keywords
- evidence
- label
- instrument
- content
- request
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000005516 engineering process Methods 0.000 claims abstract description 15
- 238000004590 computer program Methods 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000002372 labelling Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 5
- 238000009434 installation Methods 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 239000000571 coke Substances 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/14—Details of searching files based on file metadata
- G06F16/148—File search processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Technology Law (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application involves data analysis field, in particular to a kind of instrument of evidence search method, device, computer equipment and storage medium.The described method includes: receiving the retrieval request of input, retrieval request carries case by content and request content；According to semantics recognition technology from case by extracting case in content by keyword, and request keyword is extracted from request content；Retrieval obtains the instrument of evidence comprising case by keyword and request keyword from preset document data bank, and infuses evidence label for evidence files-designated, and evidence label is the label for characterizing the subject content of the instrument of evidence；Output has marked the instrument of evidence of evidence label.The utilizability of search result can be effectively improved using this method.
Description
Technical field
This application involves field of computer technology, set more particularly to a kind of instrument of evidence search method, device, computer
Standby and storage medium.
Background technique
With the improvement of living standards, the legal consciousness of people is also gradually increased, in this network technology high development and
Intelligent terminal is widely used the epoch, and user can realize more and more functions by intelligent terminals such as mobile phone or computers；It is right
Also become feasible in the retrieval instrument of evidence relevant to oneself query on the user for facing some law queries, line.
Traditionally, user is being associated between content and the instrument of evidence based on user's input for the retrieval of evidence document
Carry out, however the instrument of evidence retrieved in this way needs user voluntarily to analyze the document searched again, with
When family needs to be argued using this instrument of evidence or further retrieved, utilizability is not high.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of card of utilizability that can be improved search result
According to document retrieval method, device, computer equipment and storage medium.
A kind of instrument of evidence search method, which comprises
The retrieval request of input is received, the retrieval request carries case by content and request content；
According to semantics recognition technology from the case by extracting case in content by keyword, and mentioned from the request content
Produce request keyword；
Retrieval obtains the evidence comprising the case by keyword and the request keyword from preset document data bank
File, and evidence label is marked for the instrument of evidence, the evidence label is for characterizing in the theme of the instrument of evidence
The label of appearance；
Output marks the instrument of evidence of the good evidence label.
It is described in one of the embodiments, to mark evidence label for the instrument of evidence, comprising:
Identify the evidence item in the instrument of evidence；
Evidence item classification standard is obtained, and evidence class belonging to the evidence item is judged according to the evidence item classification standard
Type；
Evidence corresponding with the Evidence type is obtained according to the mapping relations of the Evidence type and evidence label set
Label；
The evidence label is added in the instrument of evidence.
It is described in one of the embodiments, to mark evidence label for the instrument of evidence, comprising:
The instrument of evidence is inputted in trained label model and obtains the corresponding evidence label of the instrument of evidence, institute
State label model using to a large amount of history files as training sample training obtain, can be in the instrument of evidence of input
Hold progress content analysis and obtains the model of the corresponding evidence label of the instrument of evidence；
The evidence label is added in the instrument of evidence.
In one of the embodiments, it is described the evidence label is added in the instrument of evidence before, further includes:
The decision weights for obtaining the corresponding history court verdict of evidence label in the history case of the Evidence type, according to
The decision weights are ranked up the evidence label；
It is described that the evidence label is added in the instrument of evidence, comprising:
Evidence label decision weights corresponding with the evidence label are successively added to according to the sequence after sequence
In the instrument of evidence.
The corresponding history of evidence label in the history case for obtaining the Evidence type in one of the embodiments,
After the decision weights of court verdict, further includes:
The evidence label by the decision weights not less than preset value is divided into Core Labels, by the decision weights
The evidence label lower than preset value is divided into non-core label；
It is described successively to add evidence label decision weights corresponding with the evidence label according to the sequence after sequence
It is added in the instrument of evidence, comprising:
The Core Labels and the non-core label are successively added with different notation methods according to the sequence after sequence
It is added in the instrument of evidence.
The retrieval request for receiving input in one of the embodiments, comprising:
Search field is received, is obtained in the predicted query corresponding with first search field obtained according to retrieval history
Hold field；
Show the predicted query content；
Receive selection instruction corresponding with the predicted query content of the display；
According to the selection instruction by the predicted query content of selection and the search field, spliced to obtain the inspection
Rope request.
After the output marks the well instrument of evidence of the evidence label in one of the embodiments, also wrap
It includes:
The current evidence inputted according to the instrument of evidence is received, and identifies the Evidence type of the current evidence；
The corresponding victory of the current evidence is calculated according to the corresponding history court verdict of the Evidence type of the current evidence
Tell rate；
It wins a lawsuit described in output rate.
A kind of instrument of evidence retrieval device, described device include:
Request receiving module, retrieval request for receiving input, the retrieval request carry case by content and request
Content；
Keyword-extraction module, for according to semantics recognition technology from the case by extracting case in content by keyword,
And request keyword is extracted from the request content；
Label for labelling module, for from preset document data bank retrieval obtain comprising the case by keyword and described
The instrument of evidence of keyword is requested, and marks evidence label for the instrument of evidence, the evidence label is described for characterizing
The label of the subject content of the instrument of evidence；
Output module, for exporting the instrument of evidence for marking the good evidence label.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
The step of device realizes any of the above-described the method when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of method described in any of the above embodiments is realized when row.
Above-mentioned instrument of evidence search method, device, computer equipment and storage medium, it is right respectively by semantics recognition technology
Case can be retrieved from preset document data bank and more be accorded with by the refinement of content and the keyword of request content in retrieval request
Close the instrument of evidence of user demand；And for retrieve the instrument of evidence mark be used on the evidence label argued and analyzed, for
Family, which quickly provides, argues and reference frame, effectively improves the utilizability of search result.
Detailed description of the invention
Fig. 1 is the application scenario diagram of instrument of evidence search method in one embodiment；
Fig. 2 is the flow diagram of instrument of evidence search method in one embodiment；
Fig. 3 is the flow diagram of analysis mode of winning a lawsuit in another embodiment；
Fig. 4 is the structural block diagram that the instrument of evidence retrieves device in one embodiment；
Fig. 5 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Instrument of evidence search method provided by the present application, can be applied in application environment as shown in Figure 1.Wherein, eventually
End 102 is communicated with server 104 by network by network.Technical staff issues at 104 end of server and realizes the application
The installation kit of instrument of evidence search method, terminal 102 can download installation kit and be installed from server 104, real on the terminal 102
This existing instrument of evidence search method.Wherein, terminal 102 can be, but not limited to be various personal computers, laptop, intelligence
Mobile phone, tablet computer and portable wearable device, server 104 can use independent server either multiple server groups
At server cluster realize.
In one embodiment, as shown in Fig. 2, providing a kind of instrument of evidence search method, it is applied to Fig. 1 in this way
In terminal for be illustrated, comprising the following steps:
S202, receives the retrieval request of input, and retrieval request carries case by content and request content.
Wherein, retrieval request is the request for a certain type instrument of evidence of retrieval that user inputs to terminal, be can be at end
The sentence inputted in the retrieval column provided or multiple fields are provided.The instrument of evidence in the application be log history arbitration or
The forms such as court's trial occur all types of legal cases, for by retrieve the instrument of evidence can be used as its understanding legal arbitration process,
The foundation and reference for the problems such as analyzing the law currently faced or arbitration.
Case is by the read statement that content is comprising case by keyword, such as the cause of a case, legal relation, dispute coke
The information such as point.Request content is then the requirement for needing to retrieve by content around case, can be " dispute point ", " definition ", " is assorted
" etc. show retrieve purpose sentence.
Specifically, terminal can mention after server downloading installation kit when user needs to retrieve the instrument of evidence for user
For a search interface, user can input a certain type instrument of evidence retrieval request of retrieval, this retrieval request in search interface
In should carry comprising case by keyword case by content and show retrieve purpose request content.
S204 is refined by extracting case in content by keyword, and from request content according to semantics recognition technology from case
Keyword is requested out.
Wherein, case is core central issue, the correlation method for the instrument of evidence that terminal needs to retrieve for identification by keyword
Restrain the keyword of provision, legal relation；It can be case type, such as divorce, property dispute, dispute over the right to inheritance；It can also be with
It is legal provision application, such as the judgement that a certain item of criminal law is made.Case should be at least one by keyword, user Ke Gen
Multiple superposition retrievals are carried out according to its instrument of evidence to be retrieved.Case is that case can by content by the difference of content by keyword and case
To be the more colloquial sentence of user's input, and the case case that be then terminal by keyword input according to user by content come into
Row summarizes, judgement, analyzes the obtained keyword for searching database.
Request keyword is the key that the instrument of evidence and case that terminal needs to retrieve for identification by keyword correlation
Word, for example, can be " dispute point ", " definition ", " why " etc. show retrieval purpose sentence.It requests in keyword and request
The difference of appearance is, request content can be the more colloquial sentence of user's input, and request keyword then and be terminal according to
The case of user's input is summarized by content, is judged, analyzing the obtained keyword for searching database.
Specifically, after terminal gets the case in the retrieval request of user's input by content and request content, basis respectively
Semantics recognition technology, as NLP technology (Natural Language Processing natural language processing technique) from case by content
With case for retrieval is extracted in request content by keyword and request keyword.Wherein, technical staff can also build respectively
It puts on record by key word library corresponding with request, checks the case of input by whether being included in key word library in content and request content
Part, if so, then judgement there are corresponding keywords.
S206, retrieval obtains the evidence text comprising case by keyword and request keyword from preset document data bank
Part, and evidence label is infused for evidence files-designated, evidence label is the label for characterizing the subject content of the instrument of evidence.
Wherein, preset document data bank is that technical staff analyzes the instrument of evidence of a large amount of history case, returns
The database that class is established, terminal can retrieve corresponding evidence by keyword and request keyword according to case from document data bank
File.
Evidence label is label of the technical staff according to the evidence setting for including in the instrument of evidence, can be a word
Section, is used to help the content of this instrument of evidence of customer analysis.For example, label can be divorce, property dispute, dispute over the right to inheritance etc.
Deng.
Specifically, technical staff suggests the document data bank comprising a large amount of instruments of evidence in advance, when terminal recognition goes out
After case is by keyword and request keyword, that is, this document data bank is accessed, therefrom retrieval and case are by keyword and request keyword
The corresponding instrument of evidence；After retrieving the instrument of evidence, the evidence for including in this instrument of evidence of terminal recognition is corresponding for its addition
Evidence label.
In addition, producing when terminal can not retrieve corresponding file from document data bank and showing a retrieval
Failure news, informing its retrieval content of user, there may be wrong or retrieval contents not in this document database.Together
When, this retrieval failure news can also be sent to server by terminal, so that technical staff understands the mistake occurred in user search
Accidentally, mistake is corrected by way of expanding document data bank and retrieval request automatic error-correcting.
Optionally, the document data bank in the application can also network, and the corresponding instrument of evidence is crawled from the network information and is made
It is returned for the result of retrieval.
S208, output have marked the instrument of evidence of evidence label.
Specifically, terminal exports the instrument of evidence corresponding with the retrieval request that user inputs, and exports this evidence text simultaneously
The evidence label marked in part.
Above-mentioned instrument of evidence search method, by being mentioned respectively to case in retrieval request by the keyword of content and request content
It takes, the instrument of evidence for more meeting user demand can be retrieved from preset document data bank；And the evidence text to retrieve
Part mark is used on the evidence label argued and analyze, is that user quickly provides and argues and reference frame, effectively improves inspection
The utilizability of hitch fruit.
In one embodiment, above-mentioned steps S206 is that evidence files-designated infuses evidence label, may include: identification evidence text
Evidence item in part；Obtain evidence item classification standard, and according to evidence item classification standard judge evidence item belonging to Evidence type；
Evidence label corresponding with Evidence type is obtained according to the mapping relations of the Evidence type and evidence label set；By evidence mark
Label are added in the instrument of evidence.
Wherein, evidence item is that terminal recognition goes out the evidence for including in the instrument of evidence, the expression phrase of obtained evidence, such as
In the instrument of evidence of a divorce case, may include pre-marriage agreement, real estate proves, both sides' bank transaction record etc. card
According to item.Technical staff can use the modes such as semantics recognition and identify the evidence item for including from the instrument of evidence.
Evidence item classification standard is that the evidence item that technical staff establishes according to the law corresponding relationship of evidence item is corresponding
Evidence type between mapping relations.
It is its obtained type of classifying, such as the card in above-mentioned divorce case that Evidence type, which is according to the evidence item identified,
According in file, the pre-marriage agreement that can be will identify that is divided into protocol class evidence, and real estate proves and both sides' bank transaction record
Property class evidence etc. can be divided into.
Specifically, for terminal when marking evidence label to the instrument of evidence retrieved, step is that terminal is first according to semanteme
The modes such as identification identify evidence item from the instrument of evidence retrieved, then according to the evidence item classification standard of setting to evidence
Item is classified, and Evidence type is obtained, and is that the instrument of evidence adds corresponding evidence label further according to Evidence type, evidence item is root
It is obtained according to the content recognition for including in instrument of evidence original text, reaction is usually the practical evidence of a case, and verifies
The Evidence type classified according to item is then the type for summarising practical evidence and working in a decision in a case, finally
Generate convenient for user show and refering to evidence label, be added in the instrument of evidence.
Further, technical staff can be stored as different codings when defining Evidence type and evidence label
Or the forms, such as binary coding such as feature vector etc., it can only be read when being shown to user, then by code conversion
Written form facilitates computer to identify and transmit.
In above-described embodiment, the evidence for including in the instrument of evidence retrieved is judged by the identification of evidence item, classification
Label.
In one embodiment, above-mentioned steps S206 is that evidence files-designated infuses evidence label, may include: by the instrument of evidence
It inputs in trained label model and obtains the corresponding evidence label of the instrument of evidence, label model is using to a large amount of history files
It is being obtained as training sample training, content analysis can be carried out to the content of the instrument of evidence of input, and to obtain the instrument of evidence corresponding
Evidence label model；Evidence label is added in the instrument of evidence.
Specifically, when generating evidence label, technical staff may also set up the knowledge of evidence label corresponding paragraph and sentence
Not rule is integrated, and using a large amount of history files as training sample, carries out multiple regression training, obtaining can be according to input
Instrument of evidence content detection goes out the label model of evidence label wherein included, such as deep neural network model；Terminal retrieval
To after the instrument of evidence, after instrument of evidence input label model, corresponding evidence label can be judged automatically out according to model, is
The instrument of evidence is labeled.
In above-described embodiment, label model is trained by big data analysis, it can be more accurately in analytical evidence file
The evidence label for including.
It in one embodiment, can also include: to obtain before evidence label is added in the instrument of evidence by above-mentioned steps
The decision weights of the corresponding history court verdict of evidence label in the history case of Evidence type, according to decision weights to evidence mark
Label are ranked up；Evidence label is added in the instrument of evidence by above-mentioned steps, may include: by evidence label and evidence label pair
The decision weights answered successively are added in the instrument of evidence according to the sequence after sequence.
Wherein, history court verdict is the corresponding similar case of Evidence type for including in the instrument of evidence that terminal retrieves
Court verdict.Decision weights are to influence journey of the corresponding evidence item of an Evidence type to court verdict in same type case
Degree, is to be counted to a large amount of history cases of same type, can be a quantized value.
It specifically, can be according to evidence after the corresponding evidence label of the evidence item that terminal includes in detecting the instrument of evidence
Weighing factor of the corresponding Evidence type of label in same type case for court verdict to carry out importance for evidence label
Sequence, and shown according to ranking results.For example, for property dispute case of divorcing, when one of Evidence type is
Property class evidence, then terminal can obtain divorce property dispute case type from document data bank or other external databases
Middle property class evidence determines the decision weights of court verdict in history court verdict, determines the importance of this Evidence type.
In above-described embodiment, carry out sequence discovery according to the decision weights in the corresponding history court verdict of Evidence type
Corresponding evidence label in file facilitates user to understand the evidence item in the instrument of evidence, understands the evidence retrieved convenient for user
File.
In one embodiment, the corresponding history court verdict of evidence label in the history case of above-mentioned acquisition Evidence type
Decision weights after, can also include: that decision weights are divided into Core Labels not less than the evidence label of preset value, will be certainly
Plan weight is divided into non-core label lower than the evidence label of preset value；It is then above-mentioned that evidence label is corresponding with evidence label certainly
Plan weight is successively added in the instrument of evidence according to the sequence after sequence, may include: by Core Labels and non-core label with
Different notation methods are successively added in the instrument of evidence according to the sequence after sequence.
Core Labels are evidence labels higher for court verdict influence degree in this instrument of evidence, rather than Core Labels
It is then evidence label lower for court verdict influence degree in this instrument of evidence；Technical staff can rule of thumb or go through
History judgment analysis obtains the threshold value of a decision weights, the evidence label that decision weights are higher than threshold value is set as Core Labels, certainly
Plan weight is set as non-core label not higher than the evidence label of threshold value.Evidence label is divided into Core Labels and non-core mark by terminal
Sign two classes, every class label notation methods are different, be conducive to Computer display and identification, such as can according to different coding modes, or
It is labeled as different font colors etc., every class label is shown after sorting also according to decision weights.
Further, when terminal is to user's discovery file, the simple type display side of thumbnail or title can be taken
Method, the breviary that the good evidence label of above-mentioned mark may be displayed on the file of acquisition show in content that evidence label can basis
It is divided into Core Labels and non-core label for the importance of case decision, can show Core Labels in front, and according to
Its decision weights is ranked up.Several non-core labels of front can be shown according to the importance of non-core label, and omit
Remaining non-core label.
In above-described embodiment, importance ranking and classification are carried out for evidence label, quickly understands and retrieve convenient for user
The importance of the evidence label marked in the instrument of evidence.
In one embodiment, above-mentioned steps S202 receives the retrieval request of input, may include: reception search field,
Obtain the predicted query content field corresponding with the first search field obtained according to retrieval history；Show predicted query content；
Receive selection instruction corresponding with the predicted query content of display；
According to selection instruction by the predicted query content and search field of selection, spliced to obtain retrieval request.
Search field is the content for being used to retrieve the instrument of evidence that user inputs to terminal, can be phrase and short sentence.
Terminal can according to the retrieval of historical user record in about the language in the retrieval of this search field perhaps between search field
Adopted relationship is that user recommends possible content to be searched, i.e. predicted query content, terminal shows this predicted query in display interface
Content, the field that user can select oneself to need in the relevant field of acquisition are assigned selection to terminal and are referred to as confirmation field
It enables, terminal is spliced the predicted query content of user's selection and search field to obtain retrieval request after receiving selection instruction.
In above-described embodiment, terminal can be according to the semantic relation between the retrieval record or search field of historical user
Recommend predicted query content automatically according to the search field of user's input, does not need user and input whole retrieval requests, it is real
Existing intelligent input, and the relevant field recommended can effectively avoid user from inputting retrieval request in there are in unrecognizable
Hold, reaches certain error correction effect, improve the accuracy of retrieval.
In one embodiment, refer to Fig. 3, above-mentioned steps S208 output marked evidence label the instrument of evidence it
Afterwards, it can also include analysis mode of winning a lawsuit, specifically include:
S302 receives the current evidence inputted according to the instrument of evidence, and identifies the Evidence type of current evidence.
Wherein, current evidence is the evidence label of the instrument of evidence and mark that user obtains according to retrieval, certainly in conjunction with user
The evidence for the dispute status input that body faces, can be the descriptive statement of evidence corresponding with evidence label.
Specifically, after user obtains the instrument of evidence of output at the terminal, can be inputted according to further need with
The relevant current evidence of the instrument of evidence, after terminal receives current evidence, according to semantics recognition or keyword identification technology
To identify the Evidence type of current evidence；If such as the instrument of evidence that a user search obtains is about divorce property dispute
The instrument of evidence, wherein comprising the evidences label such as divorce, property dispute, custody dispute, user can according to itself dispute status,
Current evidence corresponding with these labels is inputted, for example whether there are pre-marriage agreement, the validity period of real estate proof, assessment gold
The description of volume etc. after terminal obtains these descriptions, may recognize that " there are pre-marriage agreements " is protocol-based evidence；" real estate card
Bright validity period, the assessment amount of money " is property type evidence etc..
S304 wins a lawsuit according to the current evidence of the corresponding history court verdict calculating of the Evidence type of current evidence is corresponding
Rate.
Specifically, decision-making power of the terminal according to the Evidence type of current evidence in the court verdict of a large amount of history case
The interaction of the Evidence type of weight and multiple current evidences of input is that user calculates satisfaction according to history case analysis
The possible rate of winning a lawsuit of the case of all current evidences of input, this rate of winning a lawsuit may be a probability interval.
S306 exports rate of winning a lawsuit.
Specifically, terminal exports this rate of winning a lawsuit, and provides arbitration or lawsuit reference for user.
In above-described embodiment, terminal, can also be defeated according to the instrument of evidence according to user after the instrument of evidence that output retrieves
The current evidence entered calculates the corresponding rate of winning a lawsuit of current evidence for user, provides arbitration for user or lawsuit refers to.
It should be understood that although each step in the flow chart of Fig. 2-3 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-3
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in figure 4, providing a kind of instrument of evidence retrieval device, comprising: request receiving module
100, keyword-extraction module 200, label for labelling module 300 and output module 400, in which:
Request receiving module 100, retrieval request for receiving input, retrieval request carry case by content and request
Hold.
Keyword-extraction module 200 is used for keyword-extraction module, is used for according to semantics recognition technology from case by content
Case is extracted by keyword, and extracts request keyword from request content.
Label for labelling module 300 is obtained comprising case for retrieving from preset document data bank by keyword and request
The instrument of evidence of keyword, and evidence label is infused for evidence files-designated, evidence label is for characterizing in the theme of the instrument of evidence
The label of appearance.
Output module 400, for exporting the instrument of evidence for having marked evidence label.
In one embodiment, above-mentioned label for labelling module 300 may include:
Evidence item recognition unit, for identification evidence item in the instrument of evidence.
Type judging unit judges evidence item institute for obtaining evidence item classification standard, and according to evidence item classification standard
The Evidence type of category.
Label generation unit, for being obtained and evidence class according to the mapping relations of the Evidence type and evidence label set
The corresponding evidence label of type.
Label adding unit, for evidence label to be added in the instrument of evidence.
In one embodiment, above-mentioned label for labelling module 300 may include:
Model analysis unit obtains the corresponding card of the instrument of evidence for inputting the instrument of evidence in trained label model
According to label, label model using a large amount of history files are obtained as training sample training, can be to the evidence of input text
The content of part carries out content analysis and obtains the model of the corresponding evidence label of the instrument of evidence.
Label adding unit, for evidence label to be added in the instrument of evidence.
In one embodiment, above-mentioned instrument of evidence retrieval device can also include:
Tag sorting module, the corresponding history court verdict of evidence label in the history case for obtaining Evidence type
Decision weights are ranked up evidence label according to decision weights.
Then above-mentioned label adding unit can be also used for evidence label decision weights corresponding with evidence label according to row
Sequence after sequence is successively added in the instrument of evidence.
In one embodiment, above-mentioned instrument of evidence retrieval device can also include:
Labeling module is divided into Core Labels for the evidence label by decision weights not less than preset value, will certainly
Plan weight is divided into non-core label lower than the evidence label of preset value.
Then above-mentioned label adding unit, can be also used for by Core Labels and non-core label with different notation methods by
Sequence after phototypesetting sequence is successively added in the instrument of evidence.
In one embodiment, above-mentioned request receiving module 100 may include:
Field receiving unit, for receiving search field, obtain obtained according to retrieval history with the first search field pair
The predicted query content field answered.
Field display unit, for showing predicted query content.
Field confirmation unit, the corresponding selection instruction of predicted query content for receiving with showing.
Generation unit is requested, for, by the predicted query content and search field of selection, being spliced according to selection instruction
Obtain retrieval request.
In one embodiment, above-mentioned instrument of evidence retrieval device can also include:
Type identification module for receiving the current evidence inputted according to the instrument of evidence, and identifies the evidence of current evidence
Type.
Rate of winning a lawsuit computing module calculates current card for the corresponding history court verdict of Evidence type according to current evidence
According to corresponding rate of winning a lawsuit.
Rate of winning a lawsuit output module, for exporting rate of winning a lawsuit.
Specific about instrument of evidence retrieval device limits the limit that may refer to above for instrument of evidence search method
Fixed, details are not described herein.Modules in above-mentioned instrument of evidence retrieval device can fully or partially through software, hardware and its
Combination is to realize.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also be with
It is stored in the memory in computer equipment in a software form, in order to which processor calls the above modules of execution corresponding
Operation.
In one embodiment, a kind of computer equipment is provided, which can be terminal, internal structure
Figure can be as shown in Figure 5.The computer equipment includes processor, the memory, network interface, display connected by system bus
Screen and input unit.Wherein, the processor of the computer equipment is for providing calculating and control ability.The computer equipment is deposited
Reservoir includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system and computer journey
Sequence.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The network interface of machine equipment is used to communicate with external terminal by network connection.When the computer program is executed by processor with
Realize a kind of instrument of evidence search method.The display screen of the computer equipment can be liquid crystal display or electric ink is shown
Screen, the input unit of the computer equipment can be the touch layer covered on display screen, be also possible on computer equipment shell
Key, trace ball or the Trackpad of setting can also be external keyboard, Trackpad or mouse etc..
It will be understood by those skilled in the art that structure shown in Fig. 5, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, the processor perform the steps of the retrieval request for receiving input when executing computer program, retrieval request is taken
With case by content and request content；According to semantics recognition technology from case by extracting case in content by keyword, and from request
Request keyword is extracted in content；Retrieval is obtained comprising case by keyword and request keyword from preset document data bank
The instrument of evidence, and for evidence files-designated infuse evidence label, evidence label is the mark for characterizing the subject content of the instrument of evidence
Label；Output has marked the instrument of evidence of evidence label.
In one embodiment, realize to be evidence files-designated note evidence label, packet when processor executes computer program
It includes: the evidence item in the identification instrument of evidence；Evidence item classification standard is obtained, and evidence item institute is judged according to evidence item classification standard
The Evidence type of category；Evidence corresponding with Evidence type is obtained according to the mapping relations of the Evidence type and evidence label set
Label；Evidence label is added in the instrument of evidence.
In one embodiment, realize to be evidence files-designated note evidence label, packet when processor executes computer program
It includes: the instrument of evidence being inputted in trained label model and obtains the corresponding evidence label of the instrument of evidence, label model is to utilize
To a large amount of history files as training sample training obtain, can to the content of the instrument of evidence of input carry out content analysis obtain
To the model of the corresponding evidence label of the instrument of evidence；Evidence label is added in the instrument of evidence.
In one embodiment, that realizes when processor execution computer program is added to evidence label in the instrument of evidence
Before, further includes: the decision weights for obtaining the corresponding history court verdict of evidence label in the history case of Evidence type, according to
Decision weights are ranked up evidence label；That realizes when processor execution computer program is added to evidence label evidence text
In part, comprising: evidence label decision weights corresponding with evidence label are successively added to evidence text according to the sequence after sequence
In part.
In one embodiment, it is demonstrate,proved in the history case for the acquisition Evidence type realized when processor execution computer program
After decision weights according to the corresponding history court verdict of label, further includes: decision weights are not less than to the evidence mark of preset value
Label are divided into Core Labels, and the evidence label by decision weights lower than preset value is divided into non-core label；；Processor executes meter
That realizes when calculation machine program is successively added to evidence label decision weights corresponding with evidence label according to the sequence after sequence
In the instrument of evidence, comprising: successively add Core Labels and non-core label according to the sequence after sequence with different notation methods
It is added in the instrument of evidence.
In one embodiment, processor executes the retrieval request for the reception input realized when computer program, comprising: connects
Search field is received, the predicted query content field corresponding with the first search field obtained according to retrieval history is obtained；Display is pre-
Check and examine inquiry content；Receive selection instruction corresponding with the predicted query content of display；The pre- of selection is checked and examined according to selection instruction
Content and search field are ask, is spliced to obtain retrieval request.
In one embodiment, processor executes the evidence text that the output realized when computer program has marked evidence label
After part, further includes: receive the current evidence inputted according to the instrument of evidence, and identify the Evidence type of current evidence；According to working as
The corresponding history court verdict of the Evidence type of preceding evidence calculates the corresponding rate of winning a lawsuit of current evidence；Export rate of winning a lawsuit.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of the retrieval request for receiving input when being executed by processor, retrieval request carry case by content and
Request content；According to semantics recognition technology from case by extracting case in content by keyword, and extracts and ask from request content
Seek keyword；Retrieval obtains the instrument of evidence comprising case by keyword and request keyword from preset document data bank, and
Evidence label is infused for evidence files-designated, evidence label is the label for characterizing the subject content of the instrument of evidence；Output marks
The instrument of evidence of evidence label.
In one embodiment, realize to be evidence files-designated note evidence label when computer program is executed by processor,
It include: the evidence item identified in the instrument of evidence；Evidence item classification standard is obtained, and evidence item is judged according to evidence item classification standard
Affiliated Evidence type；Card corresponding with Evidence type is obtained according to the mapping relations of the Evidence type and evidence label set
According to label；Evidence label is added in the instrument of evidence.In one embodiment, realization when computer program is executed by processor
It is evidence files-designated note evidence label, comprising: the instrument of evidence is inputted in trained label model and obtains the instrument of evidence pair
The evidence label answered, label model using to a large amount of history files as training sample training obtain, can be to input
The content of the instrument of evidence carries out content analysis and obtains the model of the corresponding evidence label of the instrument of evidence；Evidence label is added to card
According in file.In one embodiment, that realizes when computer program is executed by processor is added to evidence label evidence text
Before in part, further includes: the decision weights of the corresponding history court verdict of evidence label in the history case of Evidence type are obtained,
Evidence label is ranked up according to decision weights；That realizes when computer program is executed by processor is added to evidence label
In the instrument of evidence, comprising: be successively added to evidence label decision weights corresponding with evidence label according to the sequence after sequence
In the instrument of evidence.In one embodiment, the history case for the acquisition Evidence type realized when computer program is executed by processor
In part after the decision weights of the corresponding history court verdict of evidence label, further includes: by decision weights not less than preset value
Evidence label is divided into Core Labels, and the evidence label by decision weights lower than preset value is divided into non-core label；；Computer
Realized when program is executed by processor by evidence label decision weights corresponding with evidence label according to the sequence after sequence according to
It is secondary to be added in the instrument of evidence, comprising: by Core Labels and non-core label with different notation methods according to suitable after sequence
Sequence is successively added to the instrument of evidence.
In one embodiment, the retrieval request for the reception input realized when computer program is executed by processor, comprising:
Search field is received, the predicted query content field corresponding with the first search field obtained according to retrieval history is obtained；Display
Predicted query content；Receive selection instruction corresponding with the predicted query content of display；According to selection instruction by the prediction of selection
Content and search field are inquired, is spliced to obtain retrieval request.
In one embodiment, the output realized when computer program is executed by processor has marked the evidence of evidence label
After file, further includes: receive the current evidence inputted according to the instrument of evidence, and identify the Evidence type of current evidence；According to
The corresponding history court verdict of Evidence type of current evidence calculates the corresponding rate of winning a lawsuit of current evidence；Export rate of winning a lawsuit.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of instrument of evidence search method, which comprises
The retrieval request of input is received, the retrieval request carries case by content and request content；
According to semantics recognition technology from the case by extracting case in content by keyword, and extracted from the request content
Request keyword；
Retrieval obtains the instrument of evidence comprising the case by keyword and the request keyword from preset document data bank,
And evidence label is marked for the instrument of evidence, the evidence label is the mark for characterizing the subject content of the instrument of evidence
Label；
Output marks the instrument of evidence of the good evidence label.
2. the method according to claim 1, wherein described mark evidence label for the instrument of evidence, comprising:
Identify the evidence item in the instrument of evidence；
Evidence item classification standard is obtained, and Evidence type belonging to the evidence item is judged according to the evidence item classification standard；
Evidence label corresponding with the Evidence type is obtained according to the mapping relations of the Evidence type and evidence label set；
The evidence label is added in the instrument of evidence.
3. the method according to claim 1, wherein described mark evidence label for the instrument of evidence, comprising:
The instrument of evidence is inputted in trained label model and obtains the corresponding evidence label of the instrument of evidence, the mark
Label model utilize to a large amount of history files as training sample it is trained obtain, can content to the instrument of evidence of input into
Row content analysis obtains the model of the corresponding evidence label of the instrument of evidence；
The evidence label is added in the instrument of evidence.
4. according to the method in claim 2 or 3, which is characterized in that described that the evidence label is added to the evidence
Before in file, further includes:
The decision weights for obtaining the corresponding history court verdict of evidence label in the history case of the Evidence type, according to described
Decision weights are ranked up the evidence label；
It is described that the evidence label is added in the instrument of evidence, comprising:
Evidence label decision weights corresponding with the evidence label are successively added to according to the sequence after sequence described
In the instrument of evidence.
5. according to the method described in claim 4, it is characterized in that, evidence in the history case for obtaining the Evidence type
After the decision weights of the corresponding history court verdict of label, further includes:
The evidence label by the decision weights not less than preset value is divided into Core Labels, and the decision weights are lower than
The evidence label of preset value is divided into non-core label；
It is described to be successively added to evidence label decision weights corresponding with the evidence label according to the sequence after sequence
In the instrument of evidence, comprising:
The Core Labels and the non-core label are successively added to different notation methods according to the sequence after sequence
In the instrument of evidence.
6. the method according to claim 1, wherein the retrieval request for receiving input, comprising:
Search field is received, the predicted query content word corresponding with first search field obtained according to retrieval history is obtained
Section；
Show the predicted query content；
Receive selection instruction corresponding with the predicted query content of the display；
According to the selection instruction by the predicted query content of selection and the search field, is spliced to obtain the retrieval and be asked
It asks.
7. the method according to claim 1, wherein the output marks the evidence of the good evidence label
After file, further includes:
The current evidence inputted according to the instrument of evidence is received, and identifies the Evidence type of the current evidence；
The corresponding rate of winning a lawsuit of the current evidence is calculated according to the corresponding history court verdict of the Evidence type of the current evidence；
It wins a lawsuit described in output rate.
8. a kind of instrument of evidence retrieves device, which is characterized in that described device includes:
Request receiving module, retrieval request for receiving input, the retrieval request carry case by content and request content；
Keyword-extraction module, for according to semantics recognition technology from the case by extracting case in content by keyword, and from
Request keyword is extracted in the request content；
Label for labelling module is obtained comprising the case for retrieving from preset document data bank by keyword and the request
The instrument of evidence of keyword, and evidence label is marked for the instrument of evidence, the evidence label is for characterizing the evidence
The label of the subject content of file；
Output module, for exporting the instrument of evidence for marking the good evidence label.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910515417 | 2019-06-14 | ||
| CN2019105154174 | 2019-06-14 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110532229A true CN110532229A (en) | 2019-12-03 |
| CN110532229B CN110532229B (en) | 2023-06-20 |
Family
ID=68660642
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910645277.2A Active CN110532229B (en) | 2019-06-14 | 2019-07-17 | Evidence file retrieval method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110532229B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111737302A (en) * | 2020-06-23 | 2020-10-02 | 中国银行股份有限公司 | Key point information query method and device |
| CN112035440A (en) * | 2020-09-01 | 2020-12-04 | 中国银行股份有限公司 | Knowledge base management method and device, electronic equipment and storage medium |
| CN113191123A (en) * | 2021-04-08 | 2021-07-30 | 中广核工程有限公司 | Indexing method and device for engineering design archive information and computer equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020052863A1 (en) * | 2000-10-31 | 2002-05-02 | Tonfu Corporation | Law retrieval system, law retrieval apparatus and law retrieval program |
| JP2003316824A (en) * | 2002-04-24 | 2003-11-07 | Toshiba Corp | Document file retrieval system, document file retrieval program and document file retrieval method |
| US20120078926A1 (en) * | 2010-09-24 | 2012-03-29 | International Business Machines Corporation | Efficient passage retrieval using document metadata |
| CN106815263A (en) * | 2015-12-01 | 2017-06-09 | 北京国双科技有限公司 | The searching method and device of legal provision |
| US20190012377A1 (en) * | 2017-07-05 | 2019-01-10 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and device for generating text tag |
-
2019
- 2019-07-17 CN CN201910645277.2A patent/CN110532229B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020052863A1 (en) * | 2000-10-31 | 2002-05-02 | Tonfu Corporation | Law retrieval system, law retrieval apparatus and law retrieval program |
| JP2003316824A (en) * | 2002-04-24 | 2003-11-07 | Toshiba Corp | Document file retrieval system, document file retrieval program and document file retrieval method |
| US20120078926A1 (en) * | 2010-09-24 | 2012-03-29 | International Business Machines Corporation | Efficient passage retrieval using document metadata |
| CN106815263A (en) * | 2015-12-01 | 2017-06-09 | 北京国双科技有限公司 | The searching method and device of legal provision |
| US20190012377A1 (en) * | 2017-07-05 | 2019-01-10 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and device for generating text tag |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111737302A (en) * | 2020-06-23 | 2020-10-02 | 中国银行股份有限公司 | Key point information query method and device |
| CN112035440A (en) * | 2020-09-01 | 2020-12-04 | 中国银行股份有限公司 | Knowledge base management method and device, electronic equipment and storage medium |
| CN112035440B (en) * | 2020-09-01 | 2023-08-08 | 中国银行股份有限公司 | Knowledge base management method, device, electronic equipment and storage medium |
| CN113191123A (en) * | 2021-04-08 | 2021-07-30 | 中广核工程有限公司 | Indexing method and device for engineering design archive information and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110532229B (en) | 2023-06-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021253904A1 (en) | Test case set generation method, apparatus and device, and computer readable storage medium | |
| CN110377632B (en) | Litigation result prediction method, litigation result prediction device, litigation result prediction computer device and litigation result prediction storage medium | |
| US20120005148A1 (en) | Integrating specialized knowledge sources into a general search service | |
| CN111459977B (en) | Conversion of natural language queries | |
| CN112288279A (en) | Business risk assessment method and device based on natural language processing and linear regression | |
| CN110532229A (en) | Instrument of evidence search method, device, computer equipment and storage medium | |
| CN109087205A (en) | Prediction technique and device, the computer equipment and readable storage medium storing program for executing of public opinion index | |
| CN109582954A (en) | Method and apparatus for output information | |
| CN110135694A (en) | Product risks appraisal procedure, device, computer equipment and storage medium | |
| CN109033427B (en) | Stock screening method and device, computer equipment and readable storage medium | |
| CN110532359A (en) | Legal provision query method, apparatus, computer equipment and storage medium | |
| CN114253990A (en) | Database query method and device, computer equipment and storage medium | |
| CN111694731A (en) | Web application test case generation method based on keyword sequence guided search | |
| Ye et al. | Deep truth discovery for pattern-based fact extraction | |
| CN117648916A (en) | Text similarity recognition model training method and text related information acquisition method | |
| CN117009373A (en) | Entity query method, query end, request end and electronic equipment | |
| US11983207B2 (en) | Method, electronic device, and computer program product for information processing | |
| CN109522407A (en) | Business connection prediction technique, device, computer equipment and storage medium | |
| CN116719915A (en) | Intelligent question-answering method, device, equipment and storage medium | |
| CN114676237A (en) | Sentence similarity determining method and device, computer equipment and storage medium | |
| CN114707510A (en) | Resource recommendation information pushing method and device, computer equipment and storage medium | |
| Zhang et al. | Answering product-related questions with heterogeneous information | |
| Ji | Readability Evaluation of Books in Chinese as a Foreign Language Using the Machine Learning Algorithm | |
| CN113095078A (en) | Associated asset determination method and device and electronic equipment | |
| CN111078972A (en) | Method and device for acquiring questioning behavior data and server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |